agora inbox for [email protected]help / color / mirror / Atom feed
[PATCH v12 1/5] Allow CREATE INDEX CONCURRENTLY on partitioned table 300+ messages / 2 participants [nested] [flat]
* [PATCH v12 1/5] Allow CREATE INDEX CONCURRENTLY on partitioned table @ 2020-06-06 22:42 Justin Pryzby <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Justin Pryzby @ 2020-06-06 22:42 UTC (permalink / raw) Note, this effectively reverts 050098b14, so take care to not reintroduce the bug it fixed. XXX: does pgstat_progress_update_param() break other commands progress ? --- doc/src/sgml/ref/create_index.sgml | 9 -- src/backend/commands/indexcmds.c | 142 ++++++++++++++++++------- src/test/regress/expected/indexing.out | 60 ++++++++++- src/test/regress/sql/indexing.sql | 18 +++- 4 files changed, 173 insertions(+), 56 deletions(-) diff --git a/doc/src/sgml/ref/create_index.sgml b/doc/src/sgml/ref/create_index.sgml index a5271a9f8f..6869a18968 100644 --- a/doc/src/sgml/ref/create_index.sgml +++ b/doc/src/sgml/ref/create_index.sgml @@ -686,15 +686,6 @@ Indexes: cannot. </para> - <para> - Concurrent builds for indexes on partitioned tables are currently not - supported. However, you may concurrently build the index on each - partition individually and then finally create the partitioned index - non-concurrently in order to reduce the time where writes to the - partitioned table will be locked out. In this case, building the - partitioned index is a metadata only operation. - </para> - </refsect2> </refsect1> diff --git a/src/backend/commands/indexcmds.c b/src/backend/commands/indexcmds.c index f9f3ff3b62..c513e8a6bd 100644 --- a/src/backend/commands/indexcmds.c +++ b/src/backend/commands/indexcmds.c @@ -68,6 +68,7 @@ /* non-export function prototypes */ +static void reindex_invalid_child_indexes(Oid indexRelationId); static bool CompareOpclassOptions(Datum *opts1, Datum *opts2, int natts); static void CheckPredicate(Expr *predicate); static void ComputeIndexAttrs(IndexInfo *indexInfo, @@ -680,17 +681,6 @@ DefineIndex(Oid relationId, partitioned = rel->rd_rel->relkind == RELKIND_PARTITIONED_TABLE; if (partitioned) { - /* - * Note: we check 'stmt->concurrent' rather than 'concurrent', so that - * the error is thrown also for temporary tables. Seems better to be - * consistent, even though we could do it on temporary table because - * we're not actually doing it concurrently. - */ - if (stmt->concurrent) - ereport(ERROR, - (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), - errmsg("cannot create index on partitioned table \"%s\" concurrently", - RelationGetRelationName(rel)))); if (stmt->excludeOpNames) ereport(ERROR, (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), @@ -1128,6 +1118,11 @@ DefineIndex(Oid relationId, if (pd->nparts != 0) flags |= INDEX_CREATE_INVALID; } + else if (concurrent && OidIsValid(parentIndexId)) + { + /* If concurrent, initially build index partitions as "invalid" */ + flags |= INDEX_CREATE_INVALID; + } if (stmt->deferrable) constr_flags |= INDEX_CONSTR_CREATE_DEFERRABLE; @@ -1183,18 +1178,29 @@ DefineIndex(Oid relationId, partdesc = RelationGetPartitionDesc(rel); if ((!stmt->relation || stmt->relation->inh) && partdesc->nparts > 0) { + /* + * Need to close the relation before recursing into children, so + * copy needed data into a longlived context. + */ + + MemoryContext ind_context = AllocSetContextCreate(PortalContext, "CREATE INDEX", + ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcontext = MemoryContextSwitchTo(ind_context); int nparts = partdesc->nparts; Oid *part_oids = palloc(sizeof(Oid) * nparts); bool invalidate_parent = false; TupleDesc parentDesc; Oid *opfamOids; + // If concurrent, maybe this should be done after excluding indexes which already exist ? pgstat_progress_update_param(PROGRESS_CREATEIDX_PARTITIONS_TOTAL, nparts); memcpy(part_oids, partdesc->oids, sizeof(Oid) * nparts); + parentDesc = CreateTupleDescCopy(RelationGetDescr(rel)); + table_close(rel, NoLock); + MemoryContextSwitchTo(oldcontext); - parentDesc = RelationGetDescr(rel); opfamOids = palloc(sizeof(Oid) * numberOfKeyAttributes); for (i = 0; i < numberOfKeyAttributes; i++) opfamOids[i] = get_opclass_family(classObjectId[i]); @@ -1237,10 +1243,12 @@ DefineIndex(Oid relationId, continue; } + oldcontext = MemoryContextSwitchTo(ind_context); childidxs = RelationGetIndexList(childrel); attmap = build_attrmap_by_name(RelationGetDescr(childrel), parentDesc); + MemoryContextSwitchTo(oldcontext); foreach(cell, childidxs) { @@ -1311,10 +1319,14 @@ DefineIndex(Oid relationId, */ if (!found) { - IndexStmt *childStmt = copyObject(stmt); + IndexStmt *childStmt; bool found_whole_row; ListCell *lc; + oldcontext = MemoryContextSwitchTo(ind_context); + childStmt = copyObject(stmt); + MemoryContextSwitchTo(oldcontext); + /* * We can't use the same index name for the child index, * so clear idxname to let the recursive invocation choose @@ -1366,10 +1378,18 @@ DefineIndex(Oid relationId, createdConstraintId, is_alter_table, check_rights, check_not_in_use, skip_build, quiet); + if (concurrent) + { + PopActiveSnapshot(); + PushActiveSnapshot(GetTransactionSnapshot()); + invalidate_parent = true; + } } - pgstat_progress_update_param(PROGRESS_CREATEIDX_PARTITIONS_DONE, - i + 1); + /* For concurrent build, this is a catalog-only stage */ + if (!concurrent) + pgstat_progress_update_param(PROGRESS_CREATEIDX_PARTITIONS_DONE, + i + 1); free_attrmap(attmap); } @@ -1379,51 +1399,42 @@ DefineIndex(Oid relationId, * invalid, this is incorrect, so update our row to invalid too. */ if (invalidate_parent) - { - Relation pg_index = table_open(IndexRelationId, RowExclusiveLock); - HeapTuple tup, - newtup; - - tup = SearchSysCache1(INDEXRELID, - ObjectIdGetDatum(indexRelationId)); - if (!HeapTupleIsValid(tup)) - elog(ERROR, "cache lookup failed for index %u", - indexRelationId); - newtup = heap_copytuple(tup); - ((Form_pg_index) GETSTRUCT(newtup))->indisvalid = false; - CatalogTupleUpdate(pg_index, &tup->t_self, newtup); - ReleaseSysCache(tup); - table_close(pg_index, RowExclusiveLock); - heap_freetuple(newtup); - } - } + index_set_state_flags(indexRelationId, INDEX_DROP_CLEAR_VALID); + } else + table_close(rel, NoLock); /* * Indexes on partitioned tables are not themselves built, so we're * done here. */ - table_close(rel, NoLock); if (!OidIsValid(parentIndexId)) + { + if (concurrent) + reindex_invalid_child_indexes(indexRelationId); + pgstat_progress_end_command(); + } + return address; } - if (!concurrent) + table_close(rel, NoLock); + if (!concurrent || OidIsValid(parentIndexId)) { - /* Close the heap and we're done, in the non-concurrent case */ - table_close(rel, NoLock); + /* + * We're done if this is the top-level index, + * or the catalog-only phase of a partition built concurrently + */ - /* If this is the top-level index, we're done. */ if (!OidIsValid(parentIndexId)) pgstat_progress_end_command(); return address; } - /* save lockrelid and locktag for below, then close rel */ + /* save lockrelid and locktag for below */ heaprelid = rel->rd_lockInfo.lockRelId; SET_LOCKTAG_RELATION(heaplocktag, heaprelid.dbId, heaprelid.relId); - table_close(rel, NoLock); /* * For a concurrent build, it's important to make the catalog entries @@ -1617,6 +1628,57 @@ DefineIndex(Oid relationId, return address; } +/* Reindex invalid child indexes created earlier */ +static void +reindex_invalid_child_indexes(Oid indexRelationId) +{ + ListCell *lc; + int npart = 0; + ReindexParams params = { .options = REINDEXOPT_CONCURRENTLY }; + + MemoryContext ind_context = AllocSetContextCreate(PortalContext, "CREATE INDEX", + ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcontext; + List *childs = find_inheritance_children(indexRelationId, ShareLock); + List *partitions = NIL; + + PreventInTransactionBlock(true, "REINDEX INDEX"); + + foreach (lc, childs) + { + Oid partoid = lfirst_oid(lc); + + pgstat_progress_update_param(PROGRESS_CREATEIDX_PARTITIONS_DONE, + npart++); + + if (get_index_isvalid(partoid) || + !RELKIND_HAS_STORAGE(get_rel_relkind(partoid))) + continue; + + /* Save partition OID */ + oldcontext = MemoryContextSwitchTo(ind_context); + partitions = lappend_oid(partitions, partoid); + MemoryContextSwitchTo(oldcontext); + } + + /* + * Process each partition listed in a separate transaction. Note that + * this commits and then starts a new transaction immediately. + */ + ReindexMultipleInternal(partitions, ¶ms); + + /* + * CIC needs to mark a partitioned index as VALID, which itself + * requires setting READY, which is unset for CIC (even though + * it's meaningless for an index without storage). + * This must be done only while holding a lock which precludes adding + * partitions. + * See also: validatePartitionedIndex(). + */ + index_set_state_flags(indexRelationId, INDEX_CREATE_SET_READY); + CommandCounterIncrement(); + index_set_state_flags(indexRelationId, INDEX_CREATE_SET_VALID); +} /* * CheckMutability diff --git a/src/test/regress/expected/indexing.out b/src/test/regress/expected/indexing.out index c93f4470c9..f04abc6897 100644 --- a/src/test/regress/expected/indexing.out +++ b/src/test/regress/expected/indexing.out @@ -50,11 +50,63 @@ select relname, relkind, relhassubclass, inhparent::regclass (8 rows) drop table idxpart; --- Some unsupported features +-- CIC on partitioned table create table idxpart (a int, b int, c text) partition by range (a); -create table idxpart1 partition of idxpart for values from (0) to (10); -create index concurrently on idxpart (a); -ERROR: cannot create index on partitioned table "idxpart" concurrently +create table idxpart1 partition of idxpart for values from (0) to (10) partition by range(a); +create table idxpart11 partition of idxpart1 for values from (0) to (10) partition by range(a); +create table idxpart111 partition of idxpart11 default partition by range(a); +create table idxpart1111 partition of idxpart111 default partition by range(a); +create table idxpart2 partition of idxpart for values from (10) to (20); +insert into idxpart2 values(10),(10); -- not unique +create index concurrently on idxpart (a); -- partitioned +create index concurrently on idxpart1 (a); -- partitioned and partition +create index concurrently on idxpart11 (a); -- partitioned and partition, with no leaves +create index concurrently on idxpart2 (a); -- leaf +create unique index concurrently on idxpart (a); -- partitioned, unique failure +ERROR: could not create unique index "idxpart2_a_idx2_ccnew" +DETAIL: Key (a)=(10) is duplicated. +\d idxpart + Partitioned table "public.idxpart" + Column | Type | Collation | Nullable | Default +--------+---------+-----------+----------+--------- + a | integer | | | + b | integer | | | + c | text | | | +Partition key: RANGE (a) +Indexes: + "idxpart_a_idx" btree (a) + "idxpart_a_idx1" UNIQUE, btree (a) INVALID +Number of partitions: 2 (Use \d+ to list them.) + +\d idxpart1 + Partitioned table "public.idxpart1" + Column | Type | Collation | Nullable | Default +--------+---------+-----------+----------+--------- + a | integer | | | + b | integer | | | + c | text | | | +Partition of: idxpart FOR VALUES FROM (0) TO (10) +Partition key: RANGE (a) +Indexes: + "idxpart1_a_idx" btree (a) INVALID + "idxpart1_a_idx1" btree (a) + "idxpart1_a_idx2" UNIQUE, btree (a) INVALID +Number of partitions: 1 (Use \d+ to list them.) + +\d idxpart2 + Table "public.idxpart2" + Column | Type | Collation | Nullable | Default +--------+---------+-----------+----------+--------- + a | integer | | | + b | integer | | | + c | text | | | +Partition of: idxpart FOR VALUES FROM (10) TO (20) +Indexes: + "idxpart2_a_idx" btree (a) + "idxpart2_a_idx1" btree (a) + "idxpart2_a_idx2" UNIQUE, btree (a) INVALID + "idxpart2_a_idx2_ccnew" UNIQUE, btree (a) INVALID + drop table idxpart; -- Verify bugfix with query on indexed partitioned table with no partitions -- https://postgr.es/m/[email protected] diff --git a/src/test/regress/sql/indexing.sql b/src/test/regress/sql/indexing.sql index 42f398b67c..3d4b6e9bc9 100644 --- a/src/test/regress/sql/indexing.sql +++ b/src/test/regress/sql/indexing.sql @@ -29,10 +29,22 @@ select relname, relkind, relhassubclass, inhparent::regclass where relname like 'idxpart%' order by relname; drop table idxpart; --- Some unsupported features +-- CIC on partitioned table create table idxpart (a int, b int, c text) partition by range (a); -create table idxpart1 partition of idxpart for values from (0) to (10); -create index concurrently on idxpart (a); +create table idxpart1 partition of idxpart for values from (0) to (10) partition by range(a); +create table idxpart11 partition of idxpart1 for values from (0) to (10) partition by range(a); +create table idxpart111 partition of idxpart11 default partition by range(a); +create table idxpart1111 partition of idxpart111 default partition by range(a); +create table idxpart2 partition of idxpart for values from (10) to (20); +insert into idxpart2 values(10),(10); -- not unique +create index concurrently on idxpart (a); -- partitioned +create index concurrently on idxpart1 (a); -- partitioned and partition +create index concurrently on idxpart11 (a); -- partitioned and partition, with no leaves +create index concurrently on idxpart2 (a); -- leaf +create unique index concurrently on idxpart (a); -- partitioned, unique failure +\d idxpart +\d idxpart1 +\d idxpart2 drop table idxpart; -- Verify bugfix with query on indexed partitioned table with no partitions -- 2.17.0 --MfFXiAuoTsnnDAfZ Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v12-0002-Add-SKIPVALID-flag-for-more-integration.patch" ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 2268cc277bc..127d4415084 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v01-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
* [PATCH 1/8] Use tuple slot to pass tuples for rewriting. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 300+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This patch tries to adopt the preferable way of handling tuples, i.e. pass the containing tuple slot rather than the actual tuple. The motivation is that heap_insert_for_repack() will need a slot in the near future, in order to call ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to to NULL, it seems more compact to pass a tuple slot as a workspace than two arrays (one for values and one for nulls). --- src/backend/access/heap/heapam_handler.c | 199 +++++++++++++---------- 1 file changed, 110 insertions(+), 89 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index bf87430cf01..4db8a16f691 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -48,14 +48,13 @@ #include "utils/rel.h" #include "utils/tuplesort.h" -static void reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate); -static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull, - BulkInsertState bistate); -static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap, - Relation NewHeap, Datum *values, bool *isnull); +static void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate); +static void heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, + BulkInsertStateData *bistate); +static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc); +static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform); static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer, HeapTuple tuple, @@ -603,11 +602,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, bool is_system_catalog; Tuplesortstate *tuplesort; TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); TupleTableSlot *slot; - int natts; - Datum *values; - bool *isnull; + TupleTableSlot *reform_slot; BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; @@ -621,11 +617,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber); - /* Preallocate values/isnull arrays */ - natts = newTupDesc->natts; - values = palloc_array(Datum, natts); - isnull = palloc_array(bool, natts); - /* * In non-concurrent mode, initialize the rewrite operation. This is not * needed in concurrent mode. @@ -699,6 +690,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, slot = table_slot_create(OldHeap, NULL); hslot = (BufferHeapTupleTableSlot *) slot; + reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsVirtual); /* * Scan through the OldHeap, either in OldIndex order or sequentially; @@ -875,11 +868,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, int64 ct_val[2]; if (!concurrent) - reform_and_rewrite_tuple(tuple, OldHeap, NewHeap, - values, isnull, rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* * In indexscan mode and also VACUUM FULL, report increase in @@ -895,8 +886,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, index_endscan(indexScan); if (tableScan != NULL) table_endscan(tableScan); - if (slot) - ExecDropSingleTupleTableSlot(slot); + ExecDropSingleTupleTableSlot(slot); /* * In scan-and-sort mode, complete the sort, then read out all live tuples @@ -916,6 +906,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); + slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap), + &TTSOpsHeapTuple); for (;;) { HeapTuple tuple; @@ -926,33 +918,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (tuple == NULL) break; + /* + * XXX Ideally we should use tuplesort_gettupleslot() above, but + * it retrieves minimal tuples and tuplesort_puttupleslot() cannot + * get the tuple descriptor from tuplesort created by + * tuplesort_begin_cluster(). + */ + ExecStoreHeapTuple(tuple, slot, false); + n_tuples += 1; if (!concurrent) - reform_and_rewrite_tuple(tuple, - OldHeap, NewHeap, - values, isnull, - rwstate); + reform_and_rewrite_tuple(slot, reform_slot, rwstate); else - heap_insert_for_repack(tuple, OldHeap, NewHeap, - values, isnull, bistate); + heap_insert_for_repack(NewHeap, slot, reform_slot, bistate); /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); } + ExecDropSingleTupleTableSlot(slot); tuplesort_end(tuplesort); } + ExecDropSingleTupleTableSlot(reform_slot); + /* Write out any remaining tuples, and fsync if needed */ if (rwstate) end_heap_rewrite(rwstate); if (bistate) FreeBulkInsertState(bistate); - - /* Clean up */ - pfree(values); - pfree(isnull); } /* @@ -2340,21 +2335,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate, * currently only known to happen as an after-effect of ALTER TABLE * SET WITHOUT OIDS. * - * So, we must reconstruct the tuple from component Datums. + * So, we must reconstruct the tuple from component Datums. 'reform' slot + * is a workspace for this reconstruction. */ static void -reform_and_rewrite_tuple(HeapTuple tuple, - Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, RewriteState rwstate) +reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform, + RewriteState rwstate) { - HeapTuple newtuple; + HeapTuple tuple, + newtuple; + bool shouldFree, + shouldFreeNew; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + /* + * The old tuple will not be modified, so do not request materialization. + * (A copy can be created for specific slot type though, e.g. + * TTSOpsMinimalTuple.) + */ + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + + /* No need to materialize, copy will be created anyway. */ + Assert(TTS_IS_VIRTUAL(reform)); + newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew); + } + else + { + newtuple = heap_copytuple(tuple); + shouldFreeNew = true; + } /* The heap rewrite module does the rest */ rewrite_heap_tuple(rwstate, tuple, newtuple); - heap_freetuple(newtuple); + if (shouldFree) + heap_freetuple(tuple); + if (shouldFreeNew) + heap_freetuple(newtuple); } /* @@ -2366,6 +2385,9 @@ reform_and_rewrite_tuple(HeapTuple tuple, * information). Thus we must use heap_insert() both during the * catch-up and here. * + * 'reform' is a slot to use for tuple "reforming", typically to get set + * values of dropped columns to NULL. + * * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops * this relation, so no logical replication subscription should need the data. @@ -2374,76 +2396,75 @@ reform_and_rewrite_tuple(HeapTuple tuple, * case. */ static void -heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull, BulkInsertState bistate) +heap_insert_for_repack(Relation rel, TupleTableSlot *src, + TupleTableSlot *reform, BulkInsertStateData *bistate) { - HeapTuple newtuple; + HeapTuple tuple; + bool shouldFree; + TupleTableSlot *slot; - newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull); + tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree); + if (tuple_needs_reform(tuple, src->tts_tupleDescriptor)) + { + clear_dropped_attributes(tuple, reform); + slot = reform; + } + else + slot = src; - heap_insert(NewHeap, newtuple, GetCurrentCommandId(true), - HEAP_INSERT_NO_LOGICAL, bistate); + /* + * clear_dropped_attributes() should have deformed the tuple, so nothing + * should depend on it now. + */ + if (shouldFree) + heap_freetuple(tuple); - heap_freetuple(newtuple); + table_tuple_insert(rel, slot, GetCurrentCommandId(true), + TABLE_INSERT_NO_LOGICAL, bistate); } -/* - * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. - * - * Deform the given tuple, set values of dropped columns to NULL, and fill in - * any values from attmissingval; then form a new tuple and return it. If no - * attributes need to be changed, a copy of the original tuple is returned. - * Caller is responsible for freeing the returned tuple. - * - * XXX this coding assumes that both relations have the same tupledesc. - */ -static HeapTuple -reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, - Datum *values, bool *isnull) +static bool +tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc) { - TupleDesc oldTupDesc = RelationGetDescr(OldHeap); - TupleDesc newTupDesc = RelationGetDescr(NewHeap); - bool needs_reform = false; - /* * A short tuple might require values from attmissing val, so activate the * coding unconditionally in that case. The value might legitimally be * NULL otherwise, so this is slightly wasteful, but it probably beats * having to test each attribute for presence of attmissingval each time. */ - if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts) - needs_reform = true; + if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts) + return true; - /* - * If the column has been dropped but a value is still present, we can - * optimize storage now by getting rid of it. - */ - if (!needs_reform) + /* Does it have dropped attributes? */ + for (int i = 0; i < tupDesc->natts; i++) { - for (int i = 0; i < newTupDesc->natts; i++) - { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped && - !heap_attisnull(tuple, i + 1, newTupDesc)) - { - needs_reform = true; - break; - } - } + if (TupleDescCompactAttr(tupDesc, i)->attisdropped && + !heap_attisnull(tuple, i + 1, tupDesc)) + return true; } - /* Skip work if no changes are needed */ - if (!needs_reform) - return heap_copytuple(tuple); + return false; +} - heap_deform_tuple(tuple, oldTupDesc, values, isnull); +/* + * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack. + * + * Set values of dropped columns to NULL, + */ +static void +clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform) +{ + TupleDesc tupDesc = reform->tts_tupleDescriptor; + + /* Assuming 'reform' is virtual, this deforms the tuple. */ + Assert(TTS_IS_VIRTUAL(reform)); + ExecForceStoreHeapTuple(tuple, reform, false); - for (int i = 0; i < newTupDesc->natts; i++) + for (int i = 0; i < tupDesc->natts; i++) { - if (TupleDescCompactAttr(newTupDesc, i)->attisdropped) - isnull[i] = true; + if (TupleDescCompactAttr(tupDesc, i)->attisdropped) + reform->tts_isnull[i] = true; } - - return heap_form_tuple(newTupDesc, values, isnull); } /* -- 2.52.0 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v02-0002-Move-functions-to-repack.c.patch ^ permalink raw reply [nested|flat] 300+ messages in thread
end of thread, other threads:[~2026-07-15 08:37 UTC | newest] Thread overview: 300+ messages (download: mbox mbox.gz follow: Atom feed) -- links below jump to the message on this page -- 2020-06-06 22:42 [PATCH v12 1/5] Allow CREATE INDEX CONCURRENTLY on partitioned table Justin Pryzby <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 1/8] Use tuple slot to pass tuples for rewriting. Antonin Houska <[email protected]>
This inbox is served by agora; see mirroring instructions for how to clone and mirror all data and code used for this inbox